Dev gzf (#1465)

zhifu gao

2024-03-11 4a7a984a5f3e3f894f86ce82e76ddd13d8a42a20

 funasr/models/ct_transformer_streaming/model.py

@@ -1,20 +1,28 @@
from typing import Any
from typing import List
from typing import Tuple
from typing import Optional
import numpy as np
import torch.nn.functional as F
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

from funasr.models.transformer.utils.nets_utils import make_pad_mask
from funasr.train_utils.device_funcs import force_gatherable
from funasr.train_utils.device_funcs import to_device
import torch
import torch.nn as nn
from funasr.models.ct_transformer.utils import split_to_mini_sentence, split_words
from funasr.utils.load_utils import load_audio_text_image_video
from funasr.models.ct_transformer.model import CTTransformer
import numpy as np
from contextlib import contextmanager
from distutils.version import LooseVersion

from funasr.register import tables
from funasr.train_utils.device_funcs import to_device
from funasr.models.ct_transformer.model import CTTransformer
from funasr.utils.load_utils import load_audio_text_image_video
from funasr.models.ct_transformer.utils import split_to_mini_sentence, split_words


if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
    from torch.cuda.amp import autocast
else:
    # Nothing to do if torch<1.6.0
    @contextmanager
    def autocast(enabled=True):
        yield


@tables.register("model_classes", "CTTransformerStreaming")
class CTTransformerStreaming(CTTransformer):
@@ -47,10 +55,8 @@

    def with_vad(self):
        return True


    
    def generate(self,
    def inference(self,
                 data_in,
                 data_lengths=None,
                 key: list = None,
@@ -167,3 +173,68 @@
    
        return results, meta_data

    def export(
        self,
        **kwargs,
    ):
    
        is_onnx = kwargs.get("type", "onnx") == "onnx"
        encoder_class = tables.encoder_classes.get(kwargs["encoder"] + "Export")
        self.encoder = encoder_class(self.encoder, onnx=is_onnx)
    
        self.forward = self._export_forward
    
        return self

    def _export_forward(self, inputs: torch.Tensor,
                text_lengths: torch.Tensor,
                vad_indexes: torch.Tensor,
                sub_masks: torch.Tensor,
                ):
        """Compute loss value from buffer sequences.

        Args:
            input (torch.Tensor): Input ids. (batch, len)
            hidden (torch.Tensor): Target ids. (batch, len)

        """
        x = self.embed(inputs)
        # mask = self._target_mask(input)
        h, _ = self.encoder(x, text_lengths, vad_indexes, sub_masks)
        y = self.decoder(h)
        return y

    def export_dummy_inputs(self):
        length = 120
        text_indexes = torch.randint(0, self.embed.num_embeddings, (1, length)).type(torch.int32)
        text_lengths = torch.tensor([length], dtype=torch.int32)
        vad_mask = torch.ones(length, length, dtype=torch.float32)[None, None, :, :]
        sub_masks = torch.ones(length, length, dtype=torch.float32)
        sub_masks = torch.tril(sub_masks).type(torch.float32)
        return (text_indexes, text_lengths, vad_mask, sub_masks[None, None, :, :])

    def export_input_names(self):
        return ['inputs', 'text_lengths', 'vad_masks', 'sub_masks']

    def export_output_names(self):
        return ['logits']

    def export_dynamic_axes(self):
        return {
            'inputs': {
                1: 'feats_length'
            },
            'vad_masks': {
                2: 'feats_length1',
                3: 'feats_length2'
            },
            'sub_masks': {
                2: 'feats_length1',
                3: 'feats_length2'
            },
            'logits': {
                1: 'logits_length'
            },
        }
    def export_name(self):
        return "model.onnx"